8f114e75239ad83bda4a02e3f28d3b95

This model is a fine-tuned version of google/umt5-xl on the Helsinki-NLP/opus_books [de-en] dataset. It achieves the following results on the evaluation set:

• Loss: 1.7371
• Data Size: 1.0
• Epoch Runtime: 659.9252
• Bleu: 12.2605

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• total_train_batch_size: 32
• total_eval_batch_size: 32
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: constant
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Data Size	Epoch Runtime	Bleu
No log	0	0	4.9825	0	45.0341	3.7882
No log	1	1286	3.2393	0.0078	49.5499	13.7745
0.0819	2	2572	2.6470	0.0156	61.9214	19.1952
0.0834	3	3858	2.2350	0.0312	74.8040	8.1440
0.1108	4	5144	1.9757	0.0625	91.8530	8.7381
2.222	5	6430	1.8775	0.125	128.0337	10.0560
2.0783	6	7716	1.7912	0.25	201.9158	10.0902
1.9385	7	9002	1.7223	0.5	357.9097	10.8471
1.8111	8.0	10288	1.6413	1.0	663.0297	11.5833
1.617	9.0	11574	1.6166	1.0	662.8222	12.1075
1.4584	10.0	12860	1.6091	1.0	658.4509	12.0952
1.3047	11.0	14146	1.6213	1.0	660.0187	12.4168
1.2394	12.0	15432	1.6416	1.0	660.7054	12.5770
1.0797	13.0	16718	1.6847	1.0	664.0519	12.5313
0.9936	14.0	18004	1.7371	1.0	659.9252	12.2605

Framework versions

• Transformers 4.57.0
• Pytorch 2.8.0+cu128
• Datasets 4.2.0
• Tokenizers 0.22.1